Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{206018,
        author = {Maheshwaran S and J. Lin Eby Chandra},
        title = {Kanvas AI: A No-Code Web Development Platform for Automating UI Design, Generation and Collaboration},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {1},
        pages = {8898-8905},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=206018},
        abstract = {Traditional web development imposes a significant barrier to entry, requiring proficiency across HTML, CSS, JavaScript, and backend frameworks before a functional application can be produced. Existing no-code platforms reduce this barrier but typically operate as closed ecosystems, fragmenting the workflow across separate tools for templating, visual editing, code generation, and conversational support. This paper introduces Kanvas AI, a unified no-code web development platform that consolidates four complementary modules into a single Django-based environment: an HTML Auto-Generator that produces tailored templates from user inputs, a GrapesJS-based drag-and-drop visual editor, a Code Generator and Error Solver that produces and repairs code snippets from natural language descriptions, and an NLP-powered conversational assistant named K.ai. The platform follows a five-layer modular architecture spanning presentation, application, AI/NLP services, external integrations, and data persistence, and supports clean export of user output as HTML, CSS, or JSON. We describe the system architecture, module-level design, and report unit and integration testing across all four modules. The deployed prototype on a public cloud environment validates the architecture’s portability beyond local development and demonstrates that an integrated no-code workflow can meaningfully reduce context switching while preserving full ownership of user output.},
        keywords = {no-code development, visual editor, GrapesJS, Django, natural language processing, code generation},
        month = {June},
        }